Guided Image Filtering

By Kaiming He, Xiaoou Tang. 2010

6,502 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Generative Visual Manipulation on the Natural Image Manifold (2016, methodology): “64 × 64), we upsample those edits using a guided image filter [33].”
Deep Image Prior (2017, background): “The resulting approach can be seen as a non-linear generalization of guided image filtering [13].”
Learning Affinity via Spatial Propagation Networks (2017, methodology): “Numerous methods explicitly design affinity matrices for image filtering [29, 10], colorization [15], matting [16] and image segmentation [14] based on the characterstics of the problem.”
Incorporating Convolution Designs into Visual Transformers (2021, background): “For the locality, it is a common assumption in visual tasks [11, 26, 9] that neighboring pixels always tend to be correlated.”
Semantic colorization with internet images (2011, methodology): “2002] and was also demonstrated as an application in [Hertzmann et al. 2001]. Irony et al. [2005] transferred colors only to points of high confidence as a first step, then treated them as user scribble input to [Levin et al.”
Lightweight Pyramid Networks for Image Deraining (2018, methodology): “[30], [31] use the guided filter [38] to”
Single Image Dehazing via Multi-scale Convolutional Neural Networks (2016, background): “However, it is computationally expensive [28,29,30] and less effective for the scenes where the color of objects are inherently similar to the atmospheric light.”
Learning Guided Convolutional Network for Depth Completion (2019, background): “As a result, this kind of local linear operator is inapplicable to fill-in sparse LiDAR points, as commented by the authors of guided filter in their conference paper [44].”
Fast End-to-End Trainable Guided Filter (2018, methodology): “The high-resolution output Oh is finally generated by a linear transformation [21], which is defined as”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “For Xdetail, we first use guided filtering [11] as a low-pass filter to split X into base and detail layers.”
Image Fusion With Guided Filtering (2013, methodology): “As demonstrated in [12], ∇O ≈ a∇I will become true, which means that only the weights in one side of the edge will be averaged.”
Pixel-Adaptive Convolutional Neural Networks (2019, background): “One class of techniques make traditional image-adaptive filters, such as bilateral filters [2, 41] and guided image filters [18] differentiable, and use them as layers inside a CNN [24, 28, 51, 11, 9, 21, 29, 8, 13, 30, 43, 45].”
D-HAZY: A dataset to evaluate quantitatively dehazing algorithms (2016, methodology): “In our evaluation we employ the dark channel prior refined based on the guided filter [34].”
Robust depth estimation for light field via spinning parallelogram operator (2016, neutral): “The calculated distance volumes at each possible depth label are filtered using guided filter [29], which can perform as an edge-preserving smoothing operator.”
Rolling Guidance Filter (2014, methodology): “Since acceleration of edge-aware filtering was well studied, many tools are available [8,19,28,22,33,32,2,1,11,12,13].”
PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, neutral): “Furthermore, many alternatives of edge-preserving filtering have been investigated, such as the guided filter [45], the domain transform filter [46], and the deep edge-aware filter [47].”
Constant Time Weighted Median Filtering for Stereo Matching and Beyond (2013, background): “Thanks to the constant time algorithm for weighted median filtering, it is feasible for us to study its performance for refining local stereo results.”